How to Use the Coder (Remote Dev) MCP in Vercel AI SDK

Q: How do I stream Coder (Remote Dev) build logs in a Vercel AI SDK app?

Use the getworkspacebuildlogs tool inside your streamText call. Pass the tool output directly to your UI components so developers watch their container builds progress line by line.

Q: How does Coder (Remote Dev) handle user authentication in Vercel AI SDK?

You pass the user's token through the authProvider in your client setup. This lets the SDK safely run checkauth and listusertokens on behalf of the active user.

Q: What happens if a Coder build hangs during a streaming session?

Your frontend can trigger cancelworkspacebuild through the SDK tools. This immediately halts the remote build process and stops the streaming text generator.

Spin up Coder (Remote Dev) workspaces with real-time UI streams using the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coder (Remote Dev) MCP to Vercel AI SDK

Create your Vinkius account to connect Coder (Remote Dev) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Coder (Remote Dev) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Coder workspace builds live using this MCP Server.

Stop making users stare at loading spinners while their remote dev environments boot up. This integration lets your Vercel AI SDK application stream build logs directly from `get_workspace_build_logs` and update the UI as progress happens. You feed the tools from `create_workspace` straight into your stream, giving developers an instant look at their setup steps. The UI updates dynamically without waiting for a final API response.

Live container diagnostics straight to React.

When a remote dev container goes sideways, users need answers fast. By combining the SDK with `get_agent_containers` and `get_agent_debug_logs`, you can render active terminal states and container lists directly inside your dashboard. Your frontend handles the streamable tool calls, rendering live JSON or styled logs as they drop. It keeps developers inside your platform instead of forcing them to run terminal diagnostics manually.

Real-time user access control and token generation.

Manage Coder credentials on the fly without page refreshes. Your Edge Functions call `create_user_token` and `check_auth` to handle security checks on demand. The Vercel AI SDK streams these permission changes directly to the browser, updating the client-side state instantly. Security policies apply immediately while keeping the interface snappy.

Setup guide

Set up Coder (Remote Dev) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Coder (Remote Dev) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Coder (Remote Dev) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coder. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Coder (Remote Dev) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Coder (Remote Dev) MCP in Vercel AI SDK

Use the `get_workspace_build_logs` tool inside your `streamText` call. Pass the tool output directly to your UI components so developers watch their container builds progress line by line.

Yes. The MCP client uses standard HTTP transports that run perfectly on Cloudflare Workers or Vercel Edge. Just hook up the `list_workspaces` tool to show active environments instantly.

You pass the user's token through the `authProvider` in your client setup. This lets the SDK safely run `check_auth` and `list_user_tokens` on behalf of the active user.

Your frontend can trigger `cancel_workspace_build` through the SDK tools. This immediately halts the remote build process and stops the streaming text generator.

Yes. Your workspace configs, credentials, and API tokens are never stored by Vinkius. Every call to `get_workspace` runs in an ephemeral, isolated sandbox that destroys itself the second the stream finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript